DeepSeek V4 Flash 0731 (Max) vs Mercury 2.5
Which is better for the money: DeepSeek V4 Flash 0731 (Max) by DeepSeek or Mercury 2.5 by Inception? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-25.
Clear winner
Verdict
Pick DeepSeek V4 Flash 0731 (Max)
Mercury 2.5 vs DeepSeek V4 Flash 0731 (Max): 64.1% less intelligence, 9.3% more cost to run the AA benchmark, and 76.6% faster end-to-end.
| Metric | DeepSeek V4 Flash 0731 (Max) | Mercury 2.5 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 34.3 | 12.3 | −64.1% Mercury 2.5 is 64.1% less intelligent |
| Total AA cost (lower is better) | $199.63 | $218.11 | +9.3% Mercury 2.5 is 9.3% more expensive |
| End-to-end time (lower is better) | 18.12s | 4.24s | −76.6% Mercury 2.5 is 76.6% faster |
| Price per 1M tokens (in / out) | $0.14 / $0.28 | $0.25 / $0.75 | |
| Input modalities | Text | Text |
Today's Pareto frontier
Against the frontier
- DeepSeek V4 Flash 0731 (Max) is off the frontier: at the same or lower cost, Claude Haiku 5.5 (Xhigh) scores 41.20 for $158.
- Mercury 2.5 is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.
DeepSeek V4 Flash 0731 (Max)Mercury 2.5Today's Pareto frontierOpen-weights frontierEvery other model
Matchup
Compare something else
Agents:
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/deepseek-v4-flash/mercury-2-5 · Markdown: /api/v1/compare/deepseek-v4-flash/mercury-2-5?format=md · llms.txt · agent skill